复制链接

克隆策略

In [6]:

# 本代码由可视化策略环境自动生成 2021年12月20日 13:59
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。


def cal_bm_close(df):
    bm_df = DataSource('bar1d_index_CN_STOCK_A').read(instruments=['000300.HIX'])
    bm_df.rename(columns={'close':'benchmark_close'}, inplace=True)
    merge_df = pd.merge(df, bm_df[['date','benchmark_close']], on='date', how='left')
    return merge_df['benchmark_close']

m12_user_functions_bigquant_run = {
    'cal_bm_close': cal_bm_close,
}
# 交易引擎：初始化函数，只执行一次
def m13_initialize_bigquant_run(context):
    df = DataSource("bar1d_index_CN_STOCK_A").read(instruments="000300.HIX",start_date="2020-01-01",end_date="2020-02-01")
    df["ma"] = df.close.rolling(5).mean()
    df["signal"] = df.apply(lambda x:1 if x.close>x.ma else 0,axis=1)
    df["signal"] = df["signal"].shift(1) #取昨日的收盘信号
    df=df[["date","signal"]]
    #信号数据
    context.signal_df = df
    #每支股票占比
    context.order_pct = 0.1
    #获取预测股票集
    context.to_buy = context.options['data'].read()
    #注册
    context.subscribe(context.instruments)
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument =0.1
    context.options['hold_days'] = 5

# 交易引擎：每个单位时间开盘前调用一次。
def m13_before_trading_start_bigquant_run(context, data):
    now = data.current_dt.strftime('%Y-%m-%d')
    context.today = data.current_dt.strftime('%Y-%m-%d')
    context.signal = context.signal_df[context.signal_df.date==now]["signal"].iloc[0]
    context.handle_flag = 0 #由于是分钟回测，每天只需要处理一次买卖
    context.sold_stock_list = []
    context.position_check = context.get_positions()
    print('日期{} 持仓 {} -----------'.format(now, context.position_check))

# 交易引擎：tick数据处理函数，每个tick执行一次
def m13_handle_tick_bigquant_run(context, data):
    pass

#卖出函数
def sell_stock(context,data,msg):
    #获取当前所有持仓
    stock_hold_now = context.get_account_positions()
    for instr in stock_hold_now:
        if instr not in context.sold_stock_list:
            #卖出可用仓位（可能有今仓）
            position = context.get_position(instr).avail_qty
            if(position>0):
                #最新价格
                price = data.current(instr, 'close')
                context.order(instr, -position, price, order_type=OrderType.MARKET)
                context.sold_stock_list.append(instr)
                print("{}卖出{} {}".format(msg,instr,position))

# 交易引擎：bar数据处理函数，每个单位执行一次
def m13_handle_data_bigquant_run(context, data):
    
    #signal为0开盘卖
    if context.signal == 1:
        msg = context.today+" 开盘"
        sell_stock(context,data,msg)
        
    current_stopwin_stock = []
    current_stoploss_stock = []
    if len(context.position_check) > 0:
        #------------------------START:止赢止损模块(含建仓期)---------------
        positions_cost={e:p.cost_price for e,p in context.get_positions().items()}
        avail_positions = {e: p.avail_qty for e, p in context.get_positions().items()}
        for instrument in positions_cost.keys():
            s = context.get_position(instrument).cost_price
            stock_cost=positions_cost[instrument]
            stock_market_price=data.current(context.symbol(instrument),'price')
            if stock_market_price/stock_cost-1>=0.2 and avail_positions[instrument] != 0:
                context.order_target(instrument, 0, order_type=OrderType.MARKET)
                print('止盈成功, 止盈标的{}'.format(instrument))
                current_stopwin_stock.append(instrument)
            elif stock_market_price/stock_cost-1 <= -0.05 and avail_positions[instrument] != 0:
                context.order_target(instrument, 0, order_type=OrderType.MARKET)
                print('止损成功, 止损标的{}'.format(instrument))
                current_stoploss_stock.append(instrument)
        if len(current_stopwin_stock)>0:
#             print(context.today,'止盈股票列表',current_stopwin_stock)
            context.sold_stock_list += current_stopwin_stock
        if len(current_stoploss_stock)>0:
#             print(context.today,'止损股票列表',current_stoploss_stock)
            context.sold_stock_list += current_stoploss_stock
        #--------------------------END: 止赢止损模块--------------------------
    
    #signal为1尾盘卖
    if context.signal == 1:
        cur_date = data.current_dt
        cur_hm =  cur_date.strftime('%H:%M')
        if(cur_hm=="14:55"):
            msg = str(cur_date)+" 尾盘"
            sell_stock(context,data,msg)
        

    #每天只处理一次
    if context.handle_flag==1:
        return
    
    #买入预测集的前5只股票
    now_data = context.to_buy[context.to_buy['date']==context.today]
    today_to_buy = []
    if not now_data.empty:
        today_to_buy = now_data.instrument[:5].to_list()
    print(context.today,"=======早盘计划买入股票 {}".format(today_to_buy))
    
    # 获取账户资金
    total_portfolio = context.portfolio.portfolio_value

    for instr in today_to_buy:
        if instr not in context.sold_stock_list:
            #最新价格
            price = data.current(instr, 'close')

            #计算买入此股票的数量，不要超过总资金的某个比例
            context.order_value(instr, total_portfolio*context.order_pct, price, order_type=OrderType.MARKET)
            print("买入{}".format(instr))
            
    context.handle_flag = 1

# 交易引擎：成交回报处理函数，每个成交发生时执行一次
def m13_handle_trade_bigquant_run(context, data):
    pass

# 交易引擎：委托回报处理函数，每个委托变化时执行一次
def m13_handle_order_bigquant_run(context, data):
    pass

# 交易引擎：盘后处理函数，每日盘后执行一次
def m13_after_trading_bigquant_run(context, data):
    pass


m1 = M.instruments.v2(
    start_date='2020-06-01',
    end_date='2020-12-01',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m2 = M.advanced_auto_labeler.v2(
    instruments=m1.data,
    label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/develop/datasource/deprecated/history_data.html
#   添加benchmark_前缀，可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.html>`_

# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -5) / shift(open, -1)

# 极值处理：用1%和99%分位的值做clip
clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))

# 将分数映射到分类，这里使用20个分类
all_wbins(label, 20)

# 过滤掉一字涨停的情况 (设置label为NaN，在后续处理和训练中会忽略NaN的label)
where(shift(high, -1) == shift(low, -1), NaN, label)
""",
    start_date='',
    end_date='',
    benchmark='000300.SHA',
    drop_na_label=True,
    cast_label_int=True
)

m3 = M.input_features.v1(
    features="""# #号开始的表示注释
# 多个特征，每行一个，可以包含基础特征和衍生特征
cond1=sum(ta_macd_dif(close_0,2,4,4),5)>sum(ta_macd_dea(close_0,2,4,4),5)
cond2=close_0>mean(close_0, 25)
cond3=sum(ta_macd_dea(close_0,2,4,4),5)>0.2"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=60
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m16.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m11 = M.input_features.v1(
    features_ds=m3.data,
    features="""# #号开始的表示注释
# 多个特征，每行一个，可以包含基础特征和衍生特征
bm_close = cal_bm_close()
stockret = close_0 / shift(close_0,1) - 1 
bmret = bm_close / shift(bm_close,1) - 1  
relative_ret=stockret-bmret
relative_ret_5=sum(relative_ret,5)
relative_ret_30=sum(relative_ret,30)"""
)

m12 = M.derived_feature_extractor.v3(
    input_data=m7.data,
    features=m11.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions=m12_user_functions_bigquant_run
)

m5 = M.dropnan.v2(
    input_data=m12.data
)

m20 = M.features_short.v1(
    input_1=m11.data
)

m4 = M.stock_ranker_train.v6(
    training_ds=m5.data,
    features=m20.data_1,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=1000,
    number_of_trees=20,
    learning_rate=0.1,
    max_bins=1023,
    feature_fraction=1,
    data_row_fraction=1,
    plot_charts=True,
    ndcg_discount_base=1,
    m_lazy_run=False
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2020-01-01'),
    end_date=T.live_run_param('trading_date', '2020-02-01'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=60
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m6 = M.chinaa_stock_filter.v1(
    input_data=m18.data,
    index_constituent_cond=['全部'],
    board_cond=['全部'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False
)

m10 = M.dropnan.v2(
    input_data=m6.data
)

m8 = M.stock_ranker_predict.v5(
    model=m4.model,
    data=m10.data,
    m_lazy_run=False
)

m13 = M.hftrade.v2(
    instruments=m9.data,
    options_data=m8.predictions,
    start_date='',
    end_date='',
    initialize=m13_initialize_bigquant_run,
    before_trading_start=m13_before_trading_start_bigquant_run,
    handle_tick=m13_handle_tick_bigquant_run,
    handle_data=m13_handle_data_bigquant_run,
    handle_trade=m13_handle_trade_bigquant_run,
    handle_order=m13_handle_order_bigquant_run,
    after_trading=m13_after_trading_bigquant_run,
    capital_base=100000,
    frequency='minute',
    price_type='真实价格',
    product_type='股票',
    before_start_days='0',
    benchmark='000300.HIX',
    plot_charts=True,
    disable_cache=False,
    show_debug_info=False,
    backtest_only=False
)

m14 = M.input_features.v1(
    features="""# #号开始的表示注释
# 多个特征，每行一个，可以包含基础特征和衍生特征
avg_turn_15/turn_0
mf_net_amount_xl_0
alpha4=close_0*avg_turn_0+close_1*avg_turn_1+close_2*avg_turn_2"""
)

m19 = M.features_short.v1(
    input_1=m14.data
)

[2021-12-20 13:58:22.417627] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-12-20 13:58:22.428483] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.430749] INFO: moduleinvoker: instruments.v2 运行完成[0.013128s].

[2021-12-20 13:58:22.442423] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-12-20 13:58:22.450067] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.452295] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.009879s].

[2021-12-20 13:58:22.456126] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-12-20 13:58:22.462041] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.463493] INFO: moduleinvoker: input_features.v1 运行完成[0.007367s].

[2021-12-20 13:58:22.474831] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-12-20 13:58:22.481427] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.483314] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.0085s].

[2021-12-20 13:58:22.493477] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-12-20 13:58:22.501960] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.504667] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.011184s].

[2021-12-20 13:58:22.515382] INFO: moduleinvoker: join.v3 开始运行..

[2021-12-20 13:58:22.525249] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.527665] INFO: moduleinvoker: join.v3 运行完成[0.012292s].

[2021-12-20 13:58:22.533335] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-12-20 13:58:22.543994] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.545578] INFO: moduleinvoker: input_features.v1 运行完成[0.012247s].

[2021-12-20 13:58:22.553688] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-12-20 13:58:22.562076] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.563702] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010017s].

[2021-12-20 13:58:22.571172] INFO: moduleinvoker: dropnan.v2 开始运行..

[2021-12-20 13:58:22.577774] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.579415] INFO: moduleinvoker: dropnan.v2 运行完成[0.008235s].

[2021-12-20 13:58:22.600228] INFO: moduleinvoker: features_short.v1 开始运行..

[2021-12-20 13:58:22.629640] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.632317] INFO: moduleinvoker: features_short.v1 运行完成[0.032101s].

[2021-12-20 13:58:22.643348] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2021-12-20 13:58:22.656010] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.748281] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[0.10493s].

[2021-12-20 13:58:22.753493] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-12-20 13:58:22.772429] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.773993] INFO: moduleinvoker: instruments.v2 运行完成[0.020517s].

[2021-12-20 13:58:22.809560] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-12-20 13:58:22.818499] INFO: moduleinvoker: 命中缓存

[2021-12-20 13:58:22.820618] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011092s].

[2021-12-20 13:58:22.832118] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-12-20 13:58:22.838151] ERROR: moduleinvoker: module name: derived_feature_extractor, module version: v3, trackeback: TypeError: __init__() takes at least 3 positional arguments (2 given)

设置评估测试数据集，查看训练曲线
[视频教程]StockRanker训练曲线

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-b99531f0349e4a418dd4241ebd60c299"}/bigcharts-data-end

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-6-69d937c7ed72> in <module>
    271 )
    272 
--> 273 m18 = M.derived_feature_extractor.v3(
    274     input_data=m17.data,
    275     date_col='date',

TypeError: __init__() takes at least 3 positional arguments (2 given)